CN111796995B - Integrated learning-based cyclic serial number usage early warning method and system - Google Patents
Integrated learning-based cyclic serial number usage early warning method and system Download PDFInfo
- Publication number
- CN111796995B CN111796995B CN202010611333.3A CN202010611333A CN111796995B CN 111796995 B CN111796995 B CN 111796995B CN 202010611333 A CN202010611333 A CN 202010611333A CN 111796995 B CN111796995 B CN 111796995B
- Authority
- CN
- China
- Prior art keywords
- serial number
- time period
- prediction
- data
- sequence number
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 125000004122 cyclic group Chemical group 0.000 title claims abstract description 31
- 238000004590 computer program Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 11
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 230000000737 periodic effect Effects 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 12
- 238000012549 training Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- JDDHUROHDHPVIO-UHFFFAOYSA-N Piperazine citrate Chemical compound C1CNCCN1.C1CNCCN1.C1CNCCN1.OC(=O)CC(O)(C(O)=O)CC(O)=O.OC(=O)CC(O)(C(O)=O)CC(O)=O JDDHUROHDHPVIO-UHFFFAOYSA-N 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 229940103147 propet Drugs 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3447—Performance evaluation by modeling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3452—Performance evaluation by statistical analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Probability & Statistics with Applications (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a cycle serial number usage early warning method and a system based on ensemble learning, wherein the method comprises the following steps: obtaining serial number data in a preset time period before the current time; predicting the serial number according to the serial number data through a preset integrated learning model to obtain the serial number usage amount of a future time period, wherein the integrated learning model is used for predicting the serial number according to a plurality of prediction algorithms and the weight of each prediction algorithm; the invention can meet the requirements of accurate monitoring and early warning of the cyclic sequence numbers under the conditions of sudden increase of the use amount and different scenes.
Description
Technical Field
The invention relates to the technical field of intelligent operation and maintenance, in particular to a cyclic serial number usage early warning method and system based on ensemble learning.
Background
The cyclic serial number is the identification of the transaction, repeated serial numbers in the same time window can cause transaction failure, so that the use of the serial number directly relates to the experience of a user, and in order to ensure that the cyclic serial number of the application cannot be reused in the same time window, the cyclic serial number variable is required to be monitored as a special resource, and the upper limit of the serial number is defined. However, the current monitoring and early warning method for the cycle sequence number cannot adapt to the sudden increase of the consumption and the accurate monitoring and early warning of the cycle sequence number in different scenes.
Disclosure of Invention
The invention aims to provide a circulating serial number usage amount early warning method based on integrated learning, which can meet the requirements of accurate monitoring and early warning of the circulating serial number under the conditions of sudden increase of usage amount and different scenes. Another object of the present invention is to provide a cyclic serial number usage early warning system based on ensemble learning. It is a further object of the invention to provide a computer device. It is a further object of the invention to provide a readable medium.
In order to achieve the above objective, the present invention discloses a cyclic sequence number usage amount early warning method based on ensemble learning, comprising:
obtaining serial number data in a preset time period before the current time;
predicting the serial number according to the serial number data through a preset integrated learning model to obtain the serial number usage amount of a future time period, wherein the integrated learning model is used for predicting the serial number according to a plurality of prediction algorithms and the weight of each prediction algorithm;
and obtaining early warning information of whether the serial number is used up in a future time period according to the serial number usage amount.
Preferably, the integrated learning model is configured to predict the serial number according to a plurality of prediction algorithms and weights of each prediction algorithm specifically includes:
the integrated learning model is used for predicting the serial number through various prediction algorithms to obtain the predicted quantity of the serial number usage in the future time period;
multiplying the predicted quantity obtained by prediction according to each prediction algorithm by the weight corresponding to the prediction algorithm to obtain the weighted predicted quantity of each prediction algorithm;
dividing the sum of the predicted amounts of all prediction algorithms by the sum of the weights yields the sequence number usage for the future time period.
Preferably, the method further comprises the step of forming the ensemble learning model.
Preferably, the forming the ensemble learning model specifically includes:
acquiring actual serial number data in two continuous time periods of a first time period and a second time period of a history;
predicting the serial number usage amount in a second time period according to the actual serial number data of the first time period by adopting various prediction algorithms respectively;
obtaining the weight of each prediction algorithm according to the predicted sequence number usage amount in the second time period and the actual sequence number data in the second time period;
and obtaining the integrated learning model according to each prediction algorithm and the corresponding weight.
Preferably, the plurality of predictive algorithms includes ARIMA algorithm, holt-winter algorithm and Prophet.
Preferably, the acquiring actual serial number data in two consecutive time periods of the first time period and the second time period of the history specifically includes:
acquiring original data of sequence number values and time stamps in two continuous time periods of a first time period and a second time period of a history;
removing abnormal data and null values in the original data to obtain processed original data;
and differentiating the processed original data according to the cyclic sequence number usage value to obtain the periodic sequence number data.
The invention also discloses a cycle serial number usage early warning system based on ensemble learning, which comprises:
the data processing module is used for obtaining serial number data in a preset time period before the current time;
the sequence number prediction module is used for predicting the sequence number according to the sequence number data through a preset integrated learning model to obtain the sequence number usage amount of the future time period, and the integrated learning model is used for predicting the sequence number according to a plurality of prediction algorithms and the weight of each prediction algorithm;
and the serial number early warning module is used for obtaining early warning information of whether the serial number is used up in a future time period according to the serial number usage amount.
Preferably, the sequence number prediction module includes:
the data prediction unit is used for predicting the serial number through a plurality of prediction algorithms to obtain the predicted quantity of the serial number usage in the future time period;
the data weighting unit is used for multiplying the predicted quantity obtained by prediction according to each prediction algorithm by the weight corresponding to the prediction algorithm to obtain the predicted quantity weighted by each prediction algorithm;
and the comprehensive prediction unit is used for dividing the sum of the predicted amounts of all the prediction algorithms by the sum of all the weights to obtain the sequence number usage amount of the future time period.
Preferably, the method further comprises a model building module for forming the integrated learning model.
Preferably, the model building module includes:
the actual data acquisition unit is used for acquiring actual serial number data in two continuous time periods of the first time period and the second time period of the history;
the actual data prediction unit is used for predicting the serial number usage amount in the second time period according to the actual serial number data of the first time period by adopting various prediction algorithms respectively;
the weight determining unit is used for obtaining the weight of each prediction algorithm according to the predicted serial number usage amount in the second time period and the actual serial number data in the second time period;
and the model construction unit is used for obtaining the integrated learning model according to each prediction algorithm and the corresponding weight.
Preferably, the actual data obtaining unit is specifically configured to obtain the sequence number value and the time stamp original data in two continuous time periods of the first time period and the second time period of the history, remove the abnormal data and the null value in the original data to obtain processed original data, and differentiate the processed original data according to the usage value of the cyclic sequence number to obtain the periodic sequence number data.
The invention also discloses a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor,
the processor, when executing the program, implements the method as described above.
The invention also discloses a computer readable medium, on which a computer program is stored,
the program, when executed by a processor, implements the method as described above.
The invention predicts the serial number usage in the future time period by adopting a plurality of prediction algorithms and obtains the serial number usage in the future time period by combining the weights of the plurality of prediction algorithms. Therefore, the invention fully considers the difference of the serial number usage in different time periods, predicts the serial number usage in the future time period after the current time period in real time according to the serial number data in the preset time period before the current time, and adapts to the special situation of sudden increase of the serial number in different time periods. Meanwhile, the invention adopts the weight for representing the prediction accuracy of each prediction algorithm to adjust the predicted serial number usage, improves the accuracy of serial number usage prediction, realizes the accurate prediction and monitoring and early warning of the cyclic serial numbers of different scenes, and meets the requirements of different types of serial number prediction.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of one embodiment of a method for early warning of usage of a cyclic sequence number based on ensemble learning;
FIG. 2 is a flowchart of a method S200 for early warning the usage of a cyclic sequence number based on ensemble learning according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method S000 for early warning of usage of a cyclic sequence number based on ensemble learning according to an embodiment of the present invention;
FIG. 4 is a flowchart of a method for early warning the usage of a cyclic sequence number based on ensemble learning according to an embodiment S010 of the present invention;
FIG. 5 is a block diagram of one embodiment of an integrated learning based cyclic sequence number usage early warning system of the present invention;
FIG. 6 is a block diagram of a sequence number prediction module of an embodiment of the cyclic sequence number usage early warning system based on ensemble learning according to the present invention;
FIG. 7 is a block diagram of a cyclic sequence number usage early warning system based on ensemble learning according to an embodiment of the present invention including a model building block;
FIG. 8 is a block diagram of a model building module of an embodiment of the cyclic sequence number usage early warning system based on ensemble learning;
fig. 9 shows a schematic diagram of a computer device suitable for use in implementing embodiments of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present application and in the foregoing figures, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
At present, there are two modes for predicting the cyclic sequence number, namely, the prediction of the sequence number resource is realized mainly by a statistical mode or by using a regression algorithm, and the phenomenon of excessive increase of the use amount of the sequence number in a special period is not considered in the prediction mode. The second method realizes the prediction of the serial number mainly through a simple prediction algorithm, and the method has higher precision compared with the first method. However, the prediction effect of a simple prediction algorithm in different scenes may be different, and the use conditions of serial numbers of different applications are different, so that the serial number prediction and monitoring early warning of all applications cannot be applied by using one prediction algorithm. Based on the method, in order to meet the demands of various serial numbers and serial number sudden increase prediction, the invention realizes the serial number intelligent prediction and monitoring and early warning method applicable to various application scenes and time by selecting various time series prediction algorithms with more applications and better prediction effect and using the prediction accuracy of test data as each algorithm weight based on the time series prediction algorithm and the integrated learning idea.
According to one aspect of the invention, the embodiment discloses a cycle sequence number usage early warning method based on ensemble learning. As shown in fig. 1, in this embodiment, the method includes:
s100: obtaining serial number data in a preset time period before the current time.
S200: and predicting the serial number according to the serial number data through a preset integrated learning model to obtain the serial number usage amount of the future time period, wherein the integrated learning model is used for predicting the serial number according to a plurality of prediction algorithms and the weight of each prediction algorithm.
S300: and obtaining early warning information of whether the serial number is used up in a future time period according to the serial number usage amount.
The invention predicts the serial number usage in the future time period by adopting a plurality of prediction algorithms and obtains the serial number usage in the future time period by combining the weights of the plurality of prediction algorithms. Therefore, the invention fully considers the difference of the serial number usage in different time periods, predicts the serial number usage in the future time period after the current time period in real time according to the serial number data in the preset time period before the current time, and adapts to the special situation of sudden increase of the serial number in different time periods. Meanwhile, the invention adopts the weight for representing the prediction accuracy of each prediction algorithm to adjust the predicted serial number usage, improves the accuracy of serial number usage prediction, realizes the accurate prediction and monitoring and early warning of the cyclic serial numbers of different scenes, and meets the requirements of different types of serial number prediction.
In a preferred embodiment, as shown in fig. 2, the integrated learning model in S200 is configured to predict the sequence number according to a plurality of prediction algorithms and the weight of each prediction algorithm, and may specifically include:
s210: the integrated learning model is used for predicting the serial number through various prediction algorithms to obtain the predicted quantity of the serial number usage in the future time period.
S220: and multiplying the predicted quantity obtained by predicting each prediction algorithm by the weight corresponding to the prediction algorithm to obtain the weighted predicted quantity of each prediction algorithm.
S230: dividing the sum of the predicted amounts of all prediction algorithms by the sum of the weights yields the sequence number usage for the future time period.
It can be appreciated that the prediction accuracy of different prediction algorithms is different for different applications and time periods, and in order to provide a prediction method applicable to different applications, the invention provides an integrated learning model according to the integrated learning idea. In forming the ensemble learning model, the prediction accuracy of each prediction algorithm is predetermined as the weight of each prediction algorithm. And determining the use amount of the sequence number which is comprehensively weighted according to the prediction algorithm and the corresponding weight, so that the prediction accuracy of the use amount of the sequence number can be improved.
In one specific example, the plurality of prediction algorithms includes ARIMA algorithm, holt-Winters algorithm, and Prophet algorithm. Wherein, for example, the prediction accuracy of ARIMA algorithm is 0.9, the prediction accuracy of Holt-winter algorithm is 0.7, and the prediction accuracy of Prophet algorithm is 0.8, which can be obtained through the prior data statistical analysis, the ensemble learning model can be expressed as the following formula:
wherein Amount is the predicted value and Pred of the serial number usage ARIMA Pred, a predicted value for the sequence number usage of ARIMA algorithm Prophet Pred, a predicted value of the sequence number usage of Prophet algorithm Holt-Winters And (3) predicting the sequence number usage amount of the Holt-windows algorithm.
In a preferred embodiment, the method further comprises a step S000 of forming the ensemble learning model. It can be appreciated that prediction accuracy of different prediction algorithms can be obtained by performing prediction analysis on the historical serial number data by using a prediction algorithm, thereby forming an integrated learning model.
In a preferred embodiment, as shown in fig. 3, the forming the ensemble learning model in S000 specifically includes:
s010: actual sequence number data is acquired for two consecutive time periods, a first time period and a second time period of the history.
S020: and respectively adopting a plurality of prediction algorithms to predict the sequence number usage amount in the second time period according to the actual sequence number data in the first time period.
S030: and obtaining the weight of each prediction algorithm according to the predicted sequence number usage amount in the second time period and the actual sequence number data in the second time period.
S040: and obtaining the integrated learning model according to each prediction algorithm and the corresponding weight.
In the preferred embodiment, a plurality of prediction algorithms are used to predict the number of used sequence numbers in the second time period based on the actual number of sequence data in the first time period. Because the serial numbers are usually formed according to a preset rule, actual serial number data can be obtained according to the use amount of the serial numbers, and the predicted actual serial number data are compared with the actual serial number data in the historical second time period, so that the prediction accuracy of a plurality of prediction algorithms can be obtained. Each predictive algorithm may be based on a large number of historical actual sequence number data to form training data and be trained using the training data. Actual serial number data in two continuous time periods of the historical first time period and the second time period are taken as test data.
In one specific example, the plurality of prediction algorithms includes ARIMA algorithm, holt-Winters algorithm, and Prophet algorithm. Firstly, training an ARIMA time sequence prediction algorithm by using training data, and calculating the ARIMA algorithm prediction accuracy by using test data. And training a Holt-windows time sequence prediction algorithm by using the training data, and calculating the prediction accuracy of the Holt-windows algorithm by using the test data. And training a propet time sequence prediction algorithm by using the training data, and calculating the propet algorithm prediction accuracy by using the test data. And then, taking the prediction accuracy of the training-based algorithm as the weight of each algorithm to realize a cycle sequence number prediction integrated learning model.
In the statistical analysis of the prediction accuracy of the prediction algorithm, an accurate range may be set according to the actual value of the sequence number in the corresponding time period, for example, a data range in which the actual value is floating up and down by a certain proportion may be selected as the accurate range. If the predicted value is within the accuracy range, it indicates that the prediction is accurate. Further, whether the prediction of the prediction algorithm at a plurality of time points is accurate or not is counted, so that the prediction accuracy of the prediction algorithm can be obtained. Wherein, preferably, a data range with an actual value which is 2% up and down can be selected as an accurate range
In a preferred embodiment, the present invention further supports online real-time updating of the ensemble learning model. Specifically, after the sequence number usage in the future time period is predicted, the actual sequence number usage in the future time period can be obtained, the prediction accuracy of each prediction algorithm is redetermined, training data can be formed according to the predicted value and the actual value of the sequence number usage in the future time period, and a plurality of prediction algorithms of the integrated learning model are trained to continuously update the integrated learning model, so that the accuracy of the sequence number usage prediction is improved.
In a preferred embodiment, as shown in fig. 4, the step of obtaining actual serial number data in two consecutive time periods of the first time period and the second time period in S010 may specifically include:
s011: raw data of sequence number values and time stamps in two continuous time periods of the first time period and the second time period of the history are obtained.
S012: and removing the abnormal data and null values in the original data to obtain the processed original data.
S013: and differentiating the processed original data according to the cyclic sequence number usage value to obtain the periodic sequence number data.
In the preferred embodiment, the serial number raw data can be obtained in real time by the SpringBoot technique. In order to apply the raw data to the predictive algorithm, the raw data may be preprocessed to obtain sequence number data having sequence number values and corresponding time stamps. The sequence number usage of the future time period can be predicted according to the sequence number value and the time stamp of the current time period. The processed serial number data can be stored in the elastic search, and can be obtained from the elastic search through regular query when the serial number data is used later.
Similarly, when the serial number data in the preset time period before the current time is obtained in S100, the preset time period may preferably be one week, the collected latest serial number value and the original data of the timestamp may be preprocessed to obtain the serial number data, and then the serial number data and the stored serial number data in one week obtained by preprocessing are combined, that is, the serial number data in the corresponding time in the stored serial number data is replaced by the latest data collected in real time, so that the serial number data in the preset time period before the current time may be obtained.
In a preferred embodiment, in S300, in the early warning information that whether the serial number is used up in the future time period is obtained according to the serial number usage amount, whether the serial number usage amount is used up in the future time period can be determined by predicting the obtained serial number usage amount and the serial number value actually used at the current time, and the early warning information is formed. If the serial number is used up, the serial number can be fed back to the user in the form of early warning information to remind the user to adjust the serial number, so that the situation that the serial number is used up and the serial number is re-used is avoided. Preferably, the serial number data may be stored in an elastic search, and the user may select a viewing time period through a query function provided by the elastic search, and acquire an actual serial number value and a predicted serial number value in the viewing time period from the elastic search in real time, where the predicted serial number value may be obtained according to a predicted serial number usage amount. The elastesearch can display the relation between the actual value and the predicted value of the serial number in the viewing time period to a user through various display modes such as line drawings.
Based on the same principle, the embodiment also discloses a cycle serial number usage early warning system based on integrated learning. As shown in fig. 5, in this embodiment, the system includes a data processing module 11, a serial number prediction module 12, and a serial number early warning module 13.
The data processing module 11 is configured to obtain serial number data in a preset time period before a current time.
The sequence number predicting module 12 is configured to predict a sequence number according to the sequence number data by using a preset ensemble learning model to obtain a sequence number usage amount in a future time period, where the ensemble learning model is configured to predict the sequence number according to a plurality of prediction algorithms and weights of each prediction algorithm.
The serial number early warning module 13 is used for obtaining early warning information of whether the serial number is used up in a future time period according to the serial number usage.
In a preferred embodiment, as shown in fig. 6, the sequence number prediction module 12 includes a data prediction unit 121, a data weighting unit 122, and an integrated prediction unit 123.
The data prediction unit 121 is configured to predict the sequence number by using multiple prediction algorithms to obtain a predicted amount of the sequence number usage in the future time period.
The data weighting unit 122 is configured to multiply the predicted quantity predicted by each prediction algorithm by the weight corresponding to the prediction algorithm to obtain a weighted predicted quantity of each prediction algorithm.
The integrated prediction unit 123 is configured to divide the sum of the predicted amounts of all prediction algorithms by the sum of all weights to obtain the sequence number usage of the future time period.
In a preferred embodiment, as shown in fig. 7, the system further comprises a model building module 10. The model building module 10 is used to form the ensemble learning model.
In a preferred embodiment, as shown in fig. 8, the model construction module 10 includes an actual data acquisition unit 101, an actual data prediction unit 102, a weight determination unit 103, and a model construction unit 104.
Wherein the actual data obtaining unit 101 is configured to obtain actual serial number data in two consecutive time periods of the first time period and the second time period.
The actual data prediction unit 102 is configured to predict the sequence number usage in the second period according to the actual sequence number data in the first period by using multiple prediction algorithms.
The weight determining unit 103 is configured to obtain a weight of each prediction algorithm according to the predicted sequence number usage amount in the second time period and the actual sequence number data in the second time period.
The model construction unit 104 is configured to obtain the integrated learning model according to each prediction algorithm and the corresponding weight.
In a preferred embodiment, the actual data obtaining unit 101 is specifically configured to obtain the sequence number value and the time-stamped original data in two consecutive time periods of the first time period and the second time period of the history, remove the abnormal data and the null value in the original data to obtain the processed original data, and differentiate the processed original data according to the cyclic sequence number usage value to obtain the periodic sequence number data.
Since the principle of solving the problem of the system is similar to that of the above method, the implementation of the system can be referred to the implementation of the method, and will not be repeated here.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. A typical implementation device is a computer device, which may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
In a typical example the computer apparatus comprises in particular a memory, a processor and a computer program stored on the memory and executable on the processor, said processor implementing the method as described above when said program is executed.
Referring now to FIG. 9, a schematic diagram of a computer device 600 suitable for use in implementing embodiments of the present application is shown.
As shown in fig. 9, the computer apparatus 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate works and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM)) 603. In the RAM603, various programs and data required for the operation of the system 600 are also stored. The CPU601, ROM602, and RAM603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a liquid crystal feedback device (LCD), and the like, and a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to the I/O interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on drive 610 as needed, so that a computer program read therefrom is mounted as needed as storage section 608.
In particular, according to embodiments of the present invention, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present application.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (9)
1. The utility model provides a circulation serial number usage early warning method based on ensemble learning which is characterized in that the method comprises the following steps:
obtaining serial number data in a preset time period before the current time;
predicting the serial number according to the serial number data through a preset integrated learning model to obtain the serial number usage amount of a future time period, wherein the integrated learning model is used for predicting the serial number according to a plurality of prediction algorithms and the weight of each prediction algorithm;
obtaining early warning information of whether the serial number is used up in a future time period according to the serial number usage amount;
further comprising the step of forming the ensemble learning model, comprising:
acquiring actual sequence number data in two continuous time periods of the first time period and the second time period of the history comprises the following steps:
acquiring original data of sequence number values and time stamps in two continuous time periods of a first time period and a second time period of a history;
removing abnormal data and null values in the original data to obtain processed original data;
and differentiating the processed original data according to the cyclic sequence number usage value to obtain the periodic sequence number data.
2. The method for early warning of the usage of a cyclic serial number based on ensemble learning according to claim 1, wherein the ensemble learning model is configured to predict the serial number according to a plurality of prediction algorithms and weights of each prediction algorithm, specifically including:
the integrated learning model is used for predicting the serial number through various prediction algorithms to obtain the predicted quantity of the serial number usage in the future time period;
multiplying the predicted quantity obtained by prediction according to each prediction algorithm by the weight corresponding to the prediction algorithm to obtain the weighted predicted quantity of each prediction algorithm;
dividing the sum of the predicted amounts of all prediction algorithms by the sum of the weights yields the sequence number usage for the future time period.
3. The method for early warning of usage of a cyclic serial number based on ensemble learning according to claim 1, wherein said forming the ensemble learning model specifically further includes:
predicting the serial number usage amount in a second time period according to the actual serial number data of the first time period by adopting various prediction algorithms respectively;
obtaining the weight of each prediction algorithm according to the predicted sequence number usage amount in the second time period and the actual sequence number data in the second time period;
and obtaining the integrated learning model according to each prediction algorithm and the corresponding weight.
4. The method for early warning of usage of cyclic sequence numbers based on ensemble learning according to claim 1, wherein the plurality of prediction algorithms includes ARIMA algorithm, holt-windows algorithm, and Prophet.
5. The utility model provides a circulation serial number usage early warning system based on ensemble learning which characterized in that includes:
the data processing module is used for obtaining serial number data in a preset time period before the current time;
the sequence number prediction module is used for predicting the sequence number according to the sequence number data through a preset integrated learning model to obtain the sequence number usage amount of the future time period, and the integrated learning model is used for predicting the sequence number according to a plurality of prediction algorithms and the weight of each prediction algorithm;
the serial number early warning module is used for obtaining early warning information of whether the serial number is used up in a future time period according to the serial number usage amount;
the model building module is used for forming the integrated learning model;
the model construction module comprises:
the actual data acquisition unit is used for acquiring actual serial number data in two continuous time periods of the first time period and the second time period of the history;
the actual data acquisition unit is specifically configured to acquire original data of sequence number values and time stamps in two continuous time periods of the first time period and the second time period of the history, remove abnormal data and null values in the original data to obtain processed original data, and differentiate the processed original data according to a cyclic sequence number usage value to obtain periodic sequence number data.
6. The ensemble learning-based cyclic sequence number usage pre-warning system of claim 5, wherein said sequence number prediction module includes:
the data prediction unit is used for predicting the serial number through a plurality of prediction algorithms to obtain the predicted quantity of the serial number usage in the future time period;
the data weighting unit is used for multiplying the predicted quantity obtained by prediction according to each prediction algorithm by the weight corresponding to the prediction algorithm to obtain the predicted quantity weighted by each prediction algorithm;
and the comprehensive prediction unit is used for dividing the sum of the predicted amounts of all the prediction algorithms by the sum of all the weights to obtain the sequence number usage amount of the future time period.
7. The ensemble learning-based cyclic sequence number usage pre-warning system as claimed in claim 5, wherein said model construction module further comprises:
the actual data prediction unit is used for predicting the serial number usage amount in the second time period according to the actual serial number data of the first time period by adopting various prediction algorithms respectively;
the weight determining unit is used for obtaining the weight of each prediction algorithm according to the predicted serial number usage amount in the second time period and the actual serial number data in the second time period;
and the model construction unit is used for obtaining the integrated learning model according to each prediction algorithm and the corresponding weight.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that,
the processor, when executing the program, implements the method of any one of claims 1-4.
9. A computer readable medium having a computer program stored thereon, characterized in that,
the program, when executed by a processor, implements the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010611333.3A CN111796995B (en) | 2020-06-30 | 2020-06-30 | Integrated learning-based cyclic serial number usage early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010611333.3A CN111796995B (en) | 2020-06-30 | 2020-06-30 | Integrated learning-based cyclic serial number usage early warning method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111796995A CN111796995A (en) | 2020-10-20 |
| CN111796995B true CN111796995B (en) | 2024-02-09 |
Family
ID=72811524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010611333.3A Active CN111796995B (en) | 2020-06-30 | 2020-06-30 | Integrated learning-based cyclic serial number usage early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111796995B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107527124A (en) * | 2017-10-13 | 2017-12-29 | 众安信息技术服务有限公司 | The method and apparatus for generating industry basic side combination forecasting |
| CN108846525A (en) * | 2018-08-02 | 2018-11-20 | 阿里巴巴集团控股有限公司 | Dealing amount of foreign exchange prediction technique and device |
| CN110275814A (en) * | 2019-06-28 | 2019-09-24 | 深圳前海微众银行股份有限公司 | A kind of monitoring method and device of operation system |
| CN110443314A (en) * | 2019-08-08 | 2019-11-12 | 中国工商银行股份有限公司 | Scenic spot passenger flow forecast method and device based on machine learning |
| CN110503235A (en) * | 2019-07-05 | 2019-11-26 | 中国平安人寿保险股份有限公司 | The prediction technique and system of time series |
| CN110515956A (en) * | 2019-09-02 | 2019-11-29 | 中国工商银行股份有限公司 | Sequence number acquisition methods, device, system, electronic equipment and storage medium |
-
2020
- 2020-06-30 CN CN202010611333.3A patent/CN111796995B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107527124A (en) * | 2017-10-13 | 2017-12-29 | 众安信息技术服务有限公司 | The method and apparatus for generating industry basic side combination forecasting |
| CN108846525A (en) * | 2018-08-02 | 2018-11-20 | 阿里巴巴集团控股有限公司 | Dealing amount of foreign exchange prediction technique and device |
| CN110275814A (en) * | 2019-06-28 | 2019-09-24 | 深圳前海微众银行股份有限公司 | A kind of monitoring method and device of operation system |
| CN110503235A (en) * | 2019-07-05 | 2019-11-26 | 中国平安人寿保险股份有限公司 | The prediction technique and system of time series |
| CN110443314A (en) * | 2019-08-08 | 2019-11-12 | 中国工商银行股份有限公司 | Scenic spot passenger flow forecast method and device based on machine learning |
| CN110515956A (en) * | 2019-09-02 | 2019-11-29 | 中国工商银行股份有限公司 | Sequence number acquisition methods, device, system, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111796995A (en) | 2020-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110400024B (en) | Order prediction method, device, equipment and computer readable storage medium | |
| CN104616173B (en) | Method and device for predicting user loss | |
| CN109039727B (en) | Deep learning-based message queue monitoring method and device | |
| CN111752706B (en) | Resource allocation method, device and storage medium | |
| US10789146B2 (en) | Forecasting resource utilization | |
| CN110795246A (en) | Resource utilization rate prediction method and device | |
| CN114500339B (en) | Node bandwidth monitoring method and device, electronic equipment and storage medium | |
| CN113407426A (en) | Server cluster capacity evaluation method and device, electronic equipment and storage medium | |
| CN111143070A (en) | Resource scheduling method and device | |
| CN111897706A (en) | Server performance prediction method, device, computer system and medium | |
| CN112398670A (en) | Flow prediction method, flow prediction device, computing equipment and computer storage medium | |
| CN111796995B (en) | Integrated learning-based cyclic serial number usage early warning method and system | |
| CN111310105B (en) | Method and device for determining labor plan | |
| CN111160614B (en) | Training method and device of resource transfer prediction model and computing equipment | |
| US11636377B1 (en) | Artificial intelligence system incorporating automatic model updates based on change point detection using time series decomposing and clustering | |
| US11651271B1 (en) | Artificial intelligence system incorporating automatic model updates based on change point detection using likelihood ratios | |
| CN114816955A (en) | Database performance prediction method and device | |
| CN115983759A (en) | Method and device for predicting demand quantity of goods, electronic equipment and storage medium | |
| CN116523446A (en) | Method, device, equipment and computer readable medium for transmitting commodity circulation quantity information | |
| CN110782063B (en) | Regional congestion degree prediction method and device | |
| US20200279199A1 (en) | Generating a completion prediction of a task | |
| CN112131468A (en) | Data processing method and device in recommendation system | |
| CN114138095B (en) | Power consumption processing method and device for internet data center IDC and readable medium | |
| CN113027414B (en) | Method and device for predicting economic recoverable reserves of crude oil | |
| CN111382754B (en) | User clustering method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |